CN108681920A - The method and system launched based on advertising creative optimization advertisement - Google Patents
The method and system launched based on advertising creative optimization advertisement Download PDFInfo
- Publication number
- CN108681920A CN108681920A CN201810454811.7A CN201810454811A CN108681920A CN 108681920 A CN108681920 A CN 108681920A CN 201810454811 A CN201810454811 A CN 201810454811A CN 108681920 A CN108681920 A CN 108681920A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- user
- marketing objectives
- launching platform
- bidding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0273—Determination of fees for advertising
- G06Q30/0275—Auctions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An embodiment of the present invention provides a kind of method and system launched based on advertising creative optimization advertisement, are related to the method that the optimization advertisement of internet environment is launched.Method includes presetting the correspondence of advertisement launching platform marketing objectives and user behavior on advertisement launching platform;Target conversion prediction model corresponding with the marketing objectives is obtained with the user's history Behavioral training prediction model on advertisement launching platform according to preset correspondence and different marketing objectives;According to the corresponding target conversion prediction model of marketing objectives, the coefficient of bidding of the advertisement is calculated;According to bid coefficient and the preset rule of bidding of each advertisement, the final bid of each advertisement is obtained, the advertisement exposure that will be won.It realizes the marketing objectives personalization optimization advertisement selected according to advertiser to launch, realizes that the income of advertisement launching platform seeks the balanced of interests with advertiser, optimize advertisement dispensing, cost has been saved under the premise of ensureing advertisement delivery effect.
Description
Technical field
The present invention relates to Internet advertising put-on methods, and in particular to one kind being based on advertising creative itself, according to different use
The feedback of family behavior, the method that optimization advertisement is launched.
Background technology
It is the advertisement material for wanting to launch by advertiser that Internet advertising, which is launched, is launched to user by advertisement delivery system
It holds, and shows a kind of advertisement dispensing release manner of reading to user, benefit from internet big data, user's portrait, efficiently meter
Ability development is calculated, the effect after advertisement is launched is improved.With progress of the epoch, and advertisement launch the abundantization, more of demand
Sample, fining, demand of the advertiser to launching effect data is more strong, different user behavior and advertisement throwing under different scenes
Putting demand, there are significant relations, therefore, carry out advertisement dispensing according to the probability that the different behaviors of user occur, can further carry
High advertisement delivery effect, while the feedback of these user behaviors further excavates abundant content for advertiser, provides deeper
The commercial value of level.
In the prior art, it is based on user's difference behavior to feed back, the method for launching advertisement to specific user mainly has following
Two schemes:First kind scheme is that experience launches method, i.e. advertisement carries out the analysis of the feedback of user behavior before launching, to determine to throw
The material put reaches desired user feedback as a result, realizing and launches maximum revenue;Second class be after through test launch charging method,
Target user is launched by the way that advertiser is specified, release platform is launched by charge method of inversion quantity, is thrown to optimize advertisement
Put effect;Third class is launched for objective optimization, i.e., selected objective target feeds back most strong user when platform is to launch advertisement.By giving
Different user behavior divides different weights or sets different threshold values to each user behavior, to reach the mesh of effect optimization
's.
In realizing process of the present invention, inventor has found that at least there are the following problems in the prior art:First kind method pair
Advertising creative relies on high, it is difficult to ensure the effect that advertisement is launched;Second class method, takes suddenly the mutual-action behavior of non-targeted user
It slightly handles, excessively roughly, it is difficult to develop new user;Third class method:Different weights, which is divided, for different user behavior selects mesh
Mark feeds back most strong user, and the method is not enough to portray feedback of the different user in specific advertising creative, is every
Kind user behavior sets different threshold values, influences advertisement and launches progress, does not account for the different effects of the different intention of advertisement itself
Fruit.
Invention content
The embodiment of the present invention provides a kind of wide according to marketing objectives optimization dispensing based on advertising creative itself context user
The method and system of announcement, can be according to the intention situation of advertisement itself, and according to the marketing objectives that advertiser selects, optimization advertisement is thrown
Effect is put, while ensureing the dispensing progress of advertisement.
On the one hand, an embodiment of the present invention provides a kind of method launched based on advertising creative optimization advertisement, the methods
Including:
The correspondence of user behavior on the marketing objectives and advertisement launching platform that default advertisement launching platform provides;
According to preset correspondence and different marketing objectives, with the user's history behavior on advertisement launching platform
Prediction model is carried out to train to obtain target conversion prediction model corresponding with the marketing objectives, the advertisement launching platform
On user's history behavior include:It is all on advertisement launching platform described in the first fixed time period set before current time
The behavior of user;
The marketing objectives and the corresponding target conversion of the marketing objectives selected when being launched according to advertisement estimates mould
Type calculates the coefficient of bidding of the advertisement;
According to bid coefficient and the preset rule of bidding of each advertisement, the final bid of each advertisement is obtained, by what is won
Advertisement exposure gives the user for meeting the stereotactic conditions selected when advertisement is launched.
On the other hand, an embodiment of the present invention provides a kind of system launched based on advertising creative optimization advertisement, the systems
System includes:
Default unit, for presetting user behavior on the marketing objectives and advertisement launching platform that advertisement launching platform provides
Correspondence;
Training unit is used for according to preset correspondence and different marketing objectives, on advertisement launching platform
User's history behavior carries out prediction model training, obtains target conversion prediction model corresponding with the marketing objectives, institute
The user's history behavior stated on advertisement launching platform includes:Advertisement described in the first fixed time period set before current time is thrown
It is laid flat the behavior of all users on platform;
Computing unit, the marketing objectives selected when for being launched according to advertisement and the corresponding target of the marketing objectives
Conversion ratio prediction model calculates the coefficient of bidding of the advertisement;
Unit of bidding obtains the final of each advertisement for bid coefficient and the preset rule of bidding according to each advertisement
The advertisement exposure won is given the user for meeting the stereotactic conditions selected when advertisement is launched by bid.
Above-mentioned technical proposal has the advantages that:Because using preset advertisement launching platform provide marketing objectives with
The correspondence of user behavior on advertisement launching platform, and according to preset correspondence, using on advertisement launching platform
The technological means of the historical behavior training prediction model of user, so having reached the target conversion obtained corresponding to marketing objectives
The technique effect of prediction model;Because using the marketing objectives selected when being launched according to advertisement and the marketing objectives pair
The target prediction model answered, calculates the coefficient of bidding of the advertisement, and according to bid coefficient and the preset rule of bidding of advertisement,
The technological means of the final bid of advertisement is calculated, so having reached according to the marketing objectives that selects when launching advertisement and each
The technique effect of advertisement is launched in the feedback behavior of itself context user of a advertising creative, optimization, while ensure that the throwing of advertisement
Degree of putting into.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is the flow chart for the method that the embodiment of the present invention 1 is launched based on advertising creative optimization advertisement;
Fig. 2 is the structural schematic diagram for the system that the embodiment of the present invention 1 is launched based on advertising creative optimization advertisement;
Fig. 3 is the flow chart for the method that the embodiment of the present invention 2 is launched based on advertising creative optimization advertisement;
Fig. 4 is the structural schematic diagram for the system that the embodiment of the present invention 2 is launched based on advertising creative optimization advertisement;
Fig. 5 is the sub-process figure for the target conversion prediction model that the embodiment of the present invention obtains corresponding to marketing objectives;
Fig. 6 is the structural schematic diagram of training unit of the embodiment of the present invention;
Fig. 7 is the schematic diagram for the target conversion prediction model that the embodiment of the present invention obtains corresponding to marketing objectives;
Fig. 8 is the schematic diagram that the embodiment of the present invention obtains target conversion reference value.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to FIG. 1, Fig. 1 is the flow chart for the method that the embodiment of the present invention 1 is launched based on advertising creative optimization advertisement;
101, the correspondence of user behavior on the marketing objectives and advertisement launching platform that advertisement launching platform provides is preset;
102, according to preset correspondence and different marketing objectives, with the user's history on advertisement launching platform
Behavior carries out prediction model training, obtains target conversion prediction model corresponding with the marketing objectives, and the advertisement is thrown
The user's history behavior being laid flat on platform includes:The advertisement launching platform in the first fixed time period set before current time
On all users behavior;
The marketing objectives and the corresponding target conversion of the marketing objectives selected when 103, being launched according to advertisement is estimated
Model calculates the coefficient of bidding of advertisement;
104, according to bid coefficient and the preset rule of bidding of each advertisement, the final bid of each advertisement is obtained, will be won
The advertisement exposure gone out gives the user for meeting the stereotactic conditions selected when advertisement is launched.
Referring to FIG. 3, Fig. 3 is the flow chart for the method that the embodiment of the present invention 2 is launched based on advertising creative optimization advertisement;
101, the correspondence of user behavior on the marketing objectives and advertisement launching platform that advertisement launching platform provides is preset;
102, according to preset correspondence and different marketing objectives, with the user's history on advertisement launching platform
Behavior carries out prediction model training, obtains target conversion prediction model corresponding with the marketing objectives, and the advertisement is thrown
The user's history behavior being laid flat on platform includes:On advertisement launching platform described in the first fixed time period set before current time
All users behavior;
105, for the active user of advertisement launching platform, the stereotactic conditions selected when being launched according to advertisement match, sieve
Advertisement complete or collected works to be exposed are selected, the stereotactic conditions that the advertisement selects when launching launch the attribute information of user for advertisement in advance;
The marketing objectives selected when 106, being launched according to each advertisement in advertisement complete or collected works to be exposed and the battalion
The corresponding target conversion prediction model of target is sold, the coefficient of bidding of each advertisement is calculated;
107, according to bid coefficient and the preset rule of bidding of each advertisement, advertisement complete or collected works to be exposed are obtained
In each advertisement final bid, the advertisement won is launched to the active user.
Preferably, the marketing objectives that the default advertisement launching platform provides, including:Increase bean vermicelli quantity, increases client
Consulting increases brand recognition;
Preferably, user behavior on the advertisement launching platform, including:Concern forwards, and comment thumbs up, and collects, and clicks
Head portrait clicks details page;
Preferably, pair of user behavior on the marketing objectives and advertisement launching platform that the default advertisement launching platform provides
It should be related to, including:It is corresponding with concern behavior to increase bean vermicelli quantity, increases client's consulting and comment, and click details page line
It is corresponding, increases brand recognition and concern, forward, comment thumbs up, and collects, and clicks head portrait, and click the row of details page
It is corresponding.
The son of target conversion prediction model corresponding to marketing objectives is obtained referring to FIG. 5, Fig. 5 is the embodiment of the present invention
Flow chart;
102.1, the behavior for collecting all users on the advertisement launching platform in the first fixed time period of setting, according to pre-
If different marketing objectives corresponding to the presence or absence of user behavior be used as training sample;
102.2, it according to click-through-rate prediction model known to training sample off-line training, obtains and the marketing objectives
Corresponding target conversion prediction model.
Preferably, the coefficient of bidding for calculating the advertisement, specifically includes:
Preset marketing objectives when being launched according to advertisement estimates mould using the corresponding target conversion of the marketing objectives
Type estimates the target conversion in present flow rate;
Target conversion in present flow rate is respectively stored in the context of corresponding advertisement, when calculating current
Between before target conversion in the second fixed time period for setting reference value, the numerical value of second fixed time period is less than
The numerical value of first fixed time period;
According to the preset marketing objectives majorized function of advertisement launching platform and the ginseng of target conversion and target conversion
Value is examined, the coefficient of bidding of each advertisement is calculated:
Preferably, the advertisement won refers to the highest advertisement of final bid;
Preferably, the computational methods of the final bid of the advertisement, specifically include:
The Numerical Control of the coefficient of bidding of advertisement is obtained revised competing in scheduled numerical intervals according to value function
Valence coefficient;
By the product of the release price of advertising presupposition and revised coefficient of bidding, the final bid as advertisement.
Referring to FIG. 2, Fig. 2 is the structural representation for the system that the embodiment of the present invention 1 is launched based on advertising creative optimization advertisement
Figure;
Default unit 21, for presetting user behavior on the marketing objectives and advertisement launching platform that advertisement launching platform provides
Correspondence;
Training unit 22 is used for according to preset correspondence and different marketing objectives, on advertisement launching platform
User's history behavior carry out prediction model training, obtain target conversion prediction model corresponding with the marketing objectives,
User's history behavior on the advertisement launching platform includes:Advertisement described in the first fixed time period set before current time
The behavior of all users on release platform;
First computing unit 23, the marketing objectives selected when for being launched according to advertisement and the marketing objectives correspond to
Target conversion prediction model, calculate the coefficient of bidding of the advertisement;
First unit 24 of bidding obtains each advertisement for bid coefficient and the preset rule of bidding according to each advertisement
Final bid, the advertisement exposure won is given to the user of stereotactic conditions for meeting and being selected when advertisement is launched.
Referring to FIG. 4, Fig. 4 is the structural representation for the system that the embodiment of the present invention 2 is launched based on advertising creative optimization advertisement
Figure;
Default unit 21, for presetting user behavior on the marketing objectives and advertisement launching platform that advertisement launching platform provides
Correspondence;
Training unit 22 is used for according to preset correspondence and different marketing objectives, on advertisement launching platform
User's history behavior carry out prediction model training, obtain target conversion prediction model corresponding with the marketing objectives,
User's history behavior on the advertisement launching platform includes:Advertisement described in the first fixed time period set before current time
The behavior of all users on release platform;
Screening unit 25, for the active user for advertisement launching platform, the orientation bar selected when being launched according to advertisement
Part matches, and filters out advertisement complete or collected works to be exposed, and the stereotactic conditions that the advertisement selects when launching launch user in advance for advertisement
Attribute information;
First computing unit 23 is additionally operable to the battalion selected when being launched according to each advertisement in advertisement complete or collected works to be exposed
Target and the corresponding target conversion prediction model of the marketing objectives are sold, the coefficient of bidding of each advertisement is calculated;
First bids unit 24, is additionally operable to bid coefficient and preset rule of bidding according to advertisement, obtains to be exposed
Advertisement complete or collected works in each advertisement final bid, the advertisement won is launched to the active user.
Preferably, in the default unit 21, the marketing objectives that the default advertisement launching platform provides, including:Increase
Bean vermicelli quantity increases client's consulting, increases brand recognition;
Preferably, in the default unit 21, user behavior on the advertisement launching platform, including:Concern, forwarding, is commented
By, it thumbs up, collects, click head portrait, click details page;
Preferably, in the default unit 21, marketing objectives and advertisement that the default advertisement launching platform provides are launched
The correspondence of user behavior on platform, including:Increasing bean vermicelli quantity and user, to pay close attention to behavior corresponding, increase client's consulting and
User comment, and it is corresponding to click details page line, increases brand recognition and is paid close attention to user, forwarded, comment thumbs up, and receives
It hides, click head portrait, and the behavior of click details page are corresponding.
Referring to FIG. 6, Fig. 6 is the structural schematic diagram of training unit of the embodiment of the present invention;
Collection module 221, for collecting all user's rows on the advertisement launching platform in the first fixed time period set
To obtain the presence or absence of the user behavior corresponding to preset different marketing objectives and being used as training sample;
Training module 222, for according to training sample known click-through-rate prediction model offline, obtaining and the battalion
Sell the corresponding target conversion prediction model of target.
Preferably, in first computing unit 23, the module of advertisement bidding coefficient is calculated, is specifically included:
First computational submodule, preset marketing objectives when for being launched according to advertisement are corresponded to using the marketing objectives
Target conversion prediction model, estimate the target conversion in present flow rate;
Second computational submodule, for the target conversion in present flow rate to be stored in the upper and lower of corresponding advertisement
Wen Zhong calculates the reference value of the target conversion in the second fixed time period set before current time, and described second fixes
The numerical value of period is less than the numerical value of the first fixed time period;
Third computational submodule, for being turned according to the preset marketing objectives majorized function of advertisement launching platform and target
The reference value of rate and target conversion calculates the coefficient of bidding of each advertisement:
Preferably, the advertisement won refers to the highest advertisement of final bid;
Preferably, it described first bids in unit 24, the computing module of the final bid for advertisement specifically includes:
Value submodule, for according to value function by the Numerical Control of the coefficient of bidding of the advertisement in scheduled numerical value
Section obtains revised coefficient of bidding;
It bids submodule, for by the product of the release price of advertising presupposition and revised coefficient of bidding, as advertisement
Final bid.
Above technical scheme has the following technical effect that, because using the user behavior corresponding to marketing objectives
The presence or absence of be used as observation sample, training advertisement launching platform user behavior for a period of time to obtain corresponding to the marketing objectives
Target conversion prediction model, so having reached different marketing objectives, using the independent training pattern of different user behavior, accuracy rate
Higher technique effect;Because using in the target conversion storage to the context of the advertisement under present flow rate, obtain
To the reference value of target conversion, the technological means of the coefficient of bidding of the advertisement is obtained, so having reached according to dispensing advertisement
When the technique effect launched of the feedback optimized advertisement of marketing objectives and advertisement itself intention context user that selects;Because
Use calculate setting the second fixed time period in target conversion reference value technological means, setting second fix when
Between section numerical value be less than setting the first fixed time period numerical value, it is excellent so do not interact between having reached different advertisements
It selects mode to be equivalent to and has carried out personalized score for each advertisement, the reference value of target conversion uses advertising creative itself
Feedback, had not only played optimization, but also do not interfere with the dispensing progress of advertisement.Because use the coefficient value that will bid be limited to it is scheduled
The technological means of numerical intervals is repaiied so having reached more balanced in system benefit and the consideration of two aspect interests of advertiser's demand
Closer to intuitive, can reach system benefit and advertiser reduces the double of cost and wins for the adjustment of coefficient of bidding after just.
The technical program is further elaborated with reference to specific Application Example:
Advertisement delivery system is according to self feature of the advertisement launching platform, according to the different marketing of different advertisers
Demand provides corresponding alternative marketing objectives, such as:Increase bean vermicelli quantity, increases client's consulting, it is well-known to increase brand
Degree etc..Advertiser, can be according to self demand when launching advertisement, and the marketing objectives for selecting ad system to provide launches backstage
It can select feature according to marketing objectives selected by advertiser in conjunction with itself, carry out the optimization of corresponding marketing objectives dispensing.How according to wide
The whole process that the selected marketing objectives of all advertisements launched on platform optimizes advertisement dispensing is accused, referred to as more marketing
Objective optimization, detailed processing procedure are as follows:
The correspondence of marketing objectives and user behavior is preset on advertisement launching platform.In conjunction with being used on advertisement launching platform
The marketing objectives that family behavior is provided with platform establishes many-to-many relationship.The marketing objectives that default advertisement launching platform provides, including:
Increase bean vermicelli quantity, increases client's consulting, increase brand recognition;User behavior on advertisement launching platform, including:Concern turns
Hair, comment, thumbs up, and collects, and clicks head portrait, clicks details page;The marketing objectives that default advertisement launching platform provides is thrown with advertisement
It is laid flat the correspondence of user behavior on platform, including:It is corresponding with user's concern behavior to increase bean vermicelli quantity, increases client's consulting
With user comment, and it is corresponding to click details page line, increases brand recognition and user and pays close attention to, forwards, and comment thumbs up,
Collection, click head portrait, and the behavior of click details page are corresponding.Advertiser selects the marketing of its concern when launching advertisement
Target, it is single to select its marketing objectives paid close attention to, and in other words, advertiser can only select the core marketing mesh that it is most paid close attention to
Mark, such as:It is to increase bean vermicelli quantity to net red dispensing ad core demand.
Showing for target conversion prediction model corresponding to marketing objectives is obtained referring to FIG. 7, Fig. 7 is the embodiment of the present invention
It is intended to;The historical data of all users on advertisement launching platform is collected, before the historical data of the user is current time, if
All behaviors of all users on advertisement launching platform described in the first fixed fixed time period, it will usually collect the selection past 30
In it on advertisement launching platform user all behaviors.For different marketing objectives, using in this target, whether there is or not mutual-action behavior works
For training sample, the data on the left of Fig. 7 in box in small box, this data are that the corresponding user behavior of marketing objectives is interactive
The presence or absence of situation, the corresponding value of different marketing objectives can be different.For different marketing objectives, using in this target, whether there is or not dynamic
As training sample, off-line training click-through-rate prediction model.The target conversion obtained corresponding to different marketing objectives is pre-
Model is estimated, such as the model 1 in Fig. 7, shown in model 2.
In a preferred embodiment 2, advertisement launching platform can be directed to the attribute information of current online user, according to each
The stereotactic conditions that advertisement selects when launching match, and participate in bidding between multiple advertisements after matching, highest advertisement of bidding will most
The screening for the step for winning, passing through eventually can obtain advertisement complete or collected works to be exposed.Such as:A, tri- advertisements of B, C, A selections
It is orientated:Beijing, man, B selections are orientated:Beijing, female, C selections are orientated:Beijing is located at Pekinese schoolgirl when one
When carrying out brush microblogging, only B, C meet stereotactic conditions, therefore B, C enter link of subsequently bidding, further according to rule of bidding between B and C
Decision is won.
Score=m*bid
Score- final bids in formula, the revised coefficients of bidding of m-, bid- advertisements preset dispensing valence when launching
Lattice.
To meet different marketing objectives, when being launched with reference to advertisement while preset release price, according to the advertisement
Target conversion of the marketing objectives selected when dispensing in present flow rate makes reward or penalty coefficient to score, that is,
Revised coefficient of bidding, calculating process are as follows:
The marketing objectives selected when advertisement is launched according to advertiser, selects the target conversion corresponding to the marketing objectives
Model estimates the target conversion otr in present flow rate, is realized especially by following formula:
Otr=f (θ, x)
F indicates that the prediction model function of advertisement launching platform setting, θ indicate that target conversion prediction model, x indicate in formula
Present flow rate;
Referring to FIG. 8, Fig. 8, which is the embodiment of the present invention, obtains the schematic diagram of target conversion reference value;
Otr is stored in the context of advertisement, the otr in the second fixed time period of setting is calculated and is used as with reference to value,
It is calculated as otr ', the numerical value of the second fixed time period of setting is less than the first fixed time period of setting, it will usually when selecting current
Between before, 3 to 5 hours this periods, especially by following formula realize:
Otr '=f (θ, x ')
F () indicates that the prediction model function of advertisement launching platform setting, θ indicate target conversion prediction model, x ' in formula
Before indicating current time, the flow in the second fixed time period of setting.
Otr and otr ' is O by marketing objectives majorized function, and it is that numberical range 1.0 is attached to calculate the coefficient o (otr) that bids
Close floating number represents present flow rate more than 1 and is better than historical traffic, otherwise represents flow and be inferior to historical traffic.Especially by such as
Lower formula is realized:
In formula:O () indicates that the preset marketing objectives majorized function of advertisement launching platform, otr indicate target conversion, otr '
Indicate that the reference value of target conversion, β indicate manual intervention coefficient.
To bid the limitation of coefficient value region, prevent Min-max marketing system income, obtaining revised bid is
Number score is used for system ranking, and the person of winning obtains chance for exposure.
Score=bidRange O (otr, otr '))
Range{O(otr,otr')}∈(0.65,1.35)
M=Range { O (otr, otr ') }
In formula, Range ()-value function.
An embodiment of the present invention provides a kind of systems for being optimized based on advertising creative and launching advertisement, and above-mentioned offer may be implemented
Embodiment of the method, concrete function, which is realized, refers to explanation in embodiment of the method, and details are not described herein.
It should be understood that the particular order or level of the step of during disclosed are the examples of illustrative methods.Based on setting
Count preference, it should be appreciated that in the process the step of particular order or level can be in the feelings for the protection domain for not departing from the disclosure
It is rearranged under condition.Appended claim to a method is not illustratively sequentially to give the element of various steps, and not
It is to be limited to the particular order or level.
In above-mentioned detailed description, various features are combined together in single embodiment, to simplify the disclosure.No
This published method should be construed to reflect such intention, that is, the embodiment of theme claimed needs to compare
The more features of feature clearly stated in each claim.On the contrary, as appended claims is reflected
Like that, the present invention is in the state fewer than whole features of disclosed single embodiment.Therefore, appended claims
It is hereby expressly incorporated into detailed description, wherein each claim is used as alone the individual preferred embodiment of the present invention.
For so that any technical staff in the art is realized or using the present invention, above to disclosed embodiment into
Description is gone.To those skilled in the art;The various modifications mode of these embodiments will be apparent from, and this
The General Principle of text definition can also be suitable for other embodiments on the basis of not departing from the spirit and scope of the disclosure.
Therefore, the disclosure is not limited to embodiments set forth herein, but most wide with principle disclosed in the present application and novel features
Range is consistent.
Described above includes the citing of one or more embodiments.Certainly, in order to describe above-described embodiment and description portion
The all possible combination of part or method is impossible, but it will be appreciated by one of ordinary skill in the art that each implementation
Example can do further combinations and permutations.Therefore, embodiment described herein is intended to cover fall into the appended claims
Protection domain in all such changes, modifications and variations.In addition, with regard to the term used in specification or claims
The mode that covers of "comprising", the word is similar to term " comprising ", just as " including " solved in the claims as link word
As releasing.In addition, the use of any one of specification in claims term "or" being to indicate " non-exclusionism
Or ".
Those skilled in the art will also be appreciated that the various illustrative components, blocks that the embodiment of the present invention is listed
(illustrative logical block), unit and step can pass through the knot of electronic hardware, computer software, or both
Conjunction is realized.To clearly show that the replaceability (interchangeability) of hardware and software, above-mentioned various explanations
Property component (illustrative components), unit and step universally describe their function.Such work(
Can be that the design requirement for depending on specific application and whole system is realized by hardware or software.Those skilled in the art
Can be for each specific function of applying, the realization of various methods can be used described, but this realization is understood not to
Range beyond protection of the embodiment of the present invention.
Various illustrative logical blocks or unit described in the embodiment of the present invention can by general processor,
Digital signal processor, application-specific integrated circuit (ASIC), field programmable gate array or other programmable logic devices, discrete gate
Or described function is realized or is operated in transistor logic, the design of discrete hardware components or any of the above described combination.General place
It can be microprocessor to manage device, and optionally, which may be any traditional processor, controller, microcontroller
Device or state machine.Processor can also be realized by the combination of computing device, such as digital signal processor and microprocessor,
Multi-microprocessor, one or more microprocessors combine a digital signal processor core or any other like configuration
To realize.
The step of method described in the embodiment of the present invention or algorithm can be directly embedded into hardware, processor execute it is soft
The combination of part module or the two.Software module can be stored in RAM memory, flash memory, ROM memory, EPROM storages
Other any form of storaging mediums in device, eeprom memory, register, hard disk, moveable magnetic disc, CD-ROM or this field
In.Illustratively, storaging medium can be connect with processor, so that processor can read information from storaging medium, and
It can be to storaging medium stored and written information.Optionally, storaging medium can also be integrated into processor.Processor and storaging medium can
To be set in ASIC, ASIC can be set in user terminal.Optionally, processor and storaging medium can also be set to use
In different components in the terminal of family.
In one or more illustrative designs, above-mentioned function described in the embodiment of the present invention can be in hardware, soft
Part, firmware or the arbitrary of this three combine to realize.If realized in software, these functions can store and computer-readable
On medium, or with one or more instruction or code form be transmitted on the medium of computer-readable.Computer readable medium includes electricity
Brain storaging medium and convenient for allow computer program to be transferred to from a place telecommunication media in other places.Storaging medium can be with
It is that any general or special computer can be with the useable medium of access.For example, such computer readable media may include but
It is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices or other
What can be used for carry or store with instruct or data structure and it is other can be by general or special computer or general or specially treated
The medium of the program code of device reading form.In addition, any connection can be properly termed computer readable medium, example
Such as, if software is to pass through a coaxial cable, fiber optic cables, double from a web-site, server or other remote resources
Twisted wire, Digital Subscriber Line (DSL) are defined with being also contained in for the wireless way for transmitting such as example infrared, wireless and microwave
In computer readable medium.The disk (disk) and disk (disc) includes compress disk, radium-shine disk, CD, DVD, floppy disk
And Blu-ray Disc, disk is usually with magnetic duplication data, and disk usually carries out optical reproduction data with laser.Combinations of the above
It can also be included in computer readable medium.
Above-described specific implementation mode has carried out further the purpose of the present invention, technical solution and advantageous effect
It is described in detail, it should be understood that the foregoing is merely the specific implementation mode of the present invention, is not intended to limit the present invention
Protection domain, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (10)
1. a kind of method launched based on advertising creative optimization advertisement, which is characterized in that the method includes:
The correspondence of user behavior on the marketing objectives and advertisement launching platform that default advertisement launching platform provides;
According to preset correspondence and different marketing objectives, carried out with the user's history behavior on advertisement launching platform
Prediction model is trained, and obtains target conversion prediction model corresponding with the marketing objectives, on the advertisement launching platform
User's history behavior include:It is all on the advertisement launching platform in the first fixed time period set before current time
User behavior;
The corresponding target conversion prediction model of marketing objectives and the marketing objectives selected when being launched according to advertisement, meter
Calculate the coefficient of bidding of advertisement;
According to bid coefficient and the preset rule of bidding of each advertisement, the final bid of each advertisement is obtained, the advertisement that will be won
It is exposed to the user for meeting the stereotactic conditions selected when advertisement is launched.
2. the method according to claim 1 launched based on advertising creative optimization advertisement, which is characterized in that the method is also
Including:
For the active user of advertisement launching platform, the stereotactic conditions selected when being launched according to advertisement match, and filter out and wait exposing
The advertisement complete or collected works of light, the stereotactic conditions that the advertisement selects when launching launch the attribute information of user for advertisement in advance;
The marketing objectives and the marketing objectives pair selected when being launched according to each advertisement in advertisement complete or collected works to be exposed
The target conversion prediction model answered calculates the coefficient of bidding of each advertisement;
According to bid coefficient and the preset rule of bidding of each advertisement, obtain each in advertisement complete or collected works to be exposed
The final bid of a advertisement launches the advertisement won to the active user.
3. the method according to claim 1 or 2 launched based on advertising creative optimization advertisement, which is characterized in that described pre-
If the marketing objectives that advertisement launching platform provides, including:Increase bean vermicelli quantity, increases client's consulting, increase brand recognition;
User behavior on the advertisement launching platform, including:Concern forwards, and comment thumbs up, and collects, and clicks head portrait, clicks
Details page;
The correspondence of user behavior, packet on the marketing objectives and advertisement launching platform that the default advertisement launching platform provides
It includes:Increase bean vermicelli quantity with concern behavior it is corresponding, increase client consulting with comment and click details page line be it is corresponding,
It is corresponding to increase brand recognition and pay close attention to, forward, comment on, thumbing up, collecting, clicking head portrait and click details page line;
It is described according to preset correspondence and different marketing objectives, with the user's history behavior on advertisement launching platform,
Prediction model training is carried out, target conversion prediction model corresponding with the marketing objectives is obtained, specifically includes:
All user behaviors on advertisement launching platform in the first fixed time period of setting are collected, according to preset different marketing
The presence or absence of user behavior corresponding to target is used as training sample;
According to click-through-rate prediction model known to training sample off-line training, mesh corresponding with the marketing objectives is obtained
Mark conversion ratio prediction model.
4. the method according to claim 1 or 2 launched based on advertising creative optimization advertisement, which is characterized in that advertisement
It bids the computational methods of coefficient, specifically includes:
Preset marketing objectives when being launched according to advertisement, using the corresponding target conversion prediction model of the marketing objectives, in advance
Estimate the target conversion in present flow rate;
Target conversion in present flow rate is stored in the context of corresponding advertisement, is set before calculating current time
The reference value of target conversion in the second fixed fixed time period, the numerical value of second fixed time period, which is less than first, to be fixed
The numerical value of period;
According to the reference of the preset marketing objectives majorized function of advertisement launching platform and target conversion and target conversion
Value, calculates the coefficient of bidding of each advertisement.
5. the method according to claim 1 or 2 launched based on advertising creative optimization advertisement, which is characterized in that the victory
The advertisement gone out refers to the highest advertisement of final bid;
The computational methods of the final bid of the advertisement, specifically include:
According to value function by the Numerical Control of the coefficient of bidding of advertisement in scheduled numerical intervals, obtaining revised bid is
Number;
By the product of the release price of advertising presupposition and revised coefficient of bidding, the final bid as advertisement.
6. a kind of optimizing the system for launching advertisement based on advertising creative, which is characterized in that described device includes:
Default unit, for preset the marketing objectives of advertisement launching platform offer on advertisement launching platform user behavior it is corresponding
Relationship;
Training unit, for according to preset correspondence and different marketing objectives, being gone through with user on advertisement launching platform
History behavior carries out prediction model training, obtains target conversion prediction model corresponding with the marketing objectives, the advertisement
User's history behavior on release platform includes:Advertisement launching platform described in the first fixed time period set before current time
On all users behavior;
First computing unit, the marketing objectives selected when for being launched according to advertisement and the corresponding target of the marketing objectives
Conversion ratio prediction model calculates the coefficient of bidding of advertisement;
First unit of bidding obtains the final of each advertisement for bid coefficient and the preset rule of bidding according to each advertisement
The advertisement exposure won is given the user for meeting the stereotactic conditions selected when advertisement is launched by bid.
7. according to claim 6 optimize the system for launching advertisement based on advertising creative, which is characterized in that described device is also
Including:
Screening unit, for the active user for advertisement launching platform, the stereotactic conditions selected when being launched according to advertisement are done
Match, filter out advertisement complete or collected works to be exposed, the stereotactic conditions that the advertisement selects when launching launch the attribute of user for advertisement in advance
Information;
First computing unit is additionally operable to the marketing mesh selected when being launched according to each advertisement in advertisement complete or collected works to be exposed
Mark and the corresponding target conversion prediction model of the marketing objectives, calculate the coefficient of bidding of each advertisement;
First bids unit, is additionally operable to bid coefficient and preset rule of bidding according to advertisement, obtains advertisement to be exposed
The final bid of each advertisement in complete or collected works launches the advertisement won to the active user.
8. optimizing the system for launching advertisement based on advertising creative described according to claim 6 or 7, which is characterized in that
In default unit, the marketing objectives that the default advertisement launching platform provides, including:Increase bean vermicelli quantity, increases client
Consulting increases brand recognition;
In default unit, user behavior on the advertisement launching platform, including:Concern forwards, and comment thumbs up, and collects, and clicks
Head portrait clicks details page;
In default unit, pair of user behavior on the marketing objectives and advertisement launching platform that the default advertisement launching platform provides
It should be related to, including:It is corresponding with user's concern behavior to increase bean vermicelli quantity, increases client's consulting and user comment, and click
Details page line is corresponding, increases brand recognition and is paid close attention to user, forwarded, comment thumbs up, and collects, and clicks head portrait, Yi Jidian
The behavior for hitting details page is corresponding;
The training unit, specifically includes:
Collection module is obtained for collecting all user behaviors in the first fixed time period set on advertisement launching platform
The presence or absence of user behavior corresponding to preset difference marketing objectives is used as training sample;
Training module, for according to click-through-rate prediction model known to training sample off-line training, obtaining and the marketing
The corresponding target conversion prediction model of target.
9. optimizing the system for launching advertisement based on advertising creative described according to claim 6 or 7, which is characterized in that described the
In one computing unit, the module for calculating advertisement bidding coefficient specifically includes:
First computational submodule, preset marketing objectives when for being launched according to advertisement, using the corresponding mesh of the marketing objectives
Conversion ratio prediction model is marked, the target conversion in present flow rate is estimated;
Second computational submodule, the context for the target conversion in present flow rate to be stored in corresponding advertisement
In, calculate current time before set the second fixed time period in target conversion reference value, it is described second fix when
Between section numerical value be less than the first fixed time period numerical value;
Third computational submodule, for according to the preset marketing objectives majorized function of advertisement launching platform and target conversion
With the reference value of target conversion, the coefficient of bidding of each advertisement is calculated.
10. optimizing the system for launching target based on advertising creative described according to claim 6 or 7, which is characterized in that the victory
The advertisement gone out refers to the highest advertisement of final bid;
The computing module of described first bids final bid that unit includes for advertisement, the computing module specifically include:
Value submodule, for according to value function by the Numerical Control of the coefficient of bidding of advertisement in scheduled numerical intervals, obtain
To revised coefficient of bidding;
Molecular modules, for by the product of the release price of advertising presupposition and revised coefficient of bidding, most as advertisement
Bid eventually.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810454811.7A CN108681920A (en) | 2018-05-14 | 2018-05-14 | The method and system launched based on advertising creative optimization advertisement |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810454811.7A CN108681920A (en) | 2018-05-14 | 2018-05-14 | The method and system launched based on advertising creative optimization advertisement |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108681920A true CN108681920A (en) | 2018-10-19 |
Family
ID=63806403
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810454811.7A Pending CN108681920A (en) | 2018-05-14 | 2018-05-14 | The method and system launched based on advertising creative optimization advertisement |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108681920A (en) |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109598542A (en) * | 2018-11-20 | 2019-04-09 | 阿里巴巴集团控股有限公司 | A kind of put-on method, device and the electronic equipment of equity of marketing |
CN109711866A (en) * | 2018-12-07 | 2019-05-03 | 中国银行股份有限公司 | A kind of bank advertising put-on method, apparatus and system |
CN110135905A (en) * | 2019-05-13 | 2019-08-16 | 重庆天蓬网络有限公司 | Advertisement placement method, system, medium and electronic equipment |
CN110969490A (en) * | 2019-12-17 | 2020-04-07 | 天津亿玛科技有限公司 | Advertisement putting method and device |
CN111062746A (en) * | 2019-12-06 | 2020-04-24 | 微梦创科网络科技(中国)有限公司 | Advertisement flow estimation method and device and electronic equipment |
CN111105268A (en) * | 2019-11-28 | 2020-05-05 | 微梦创科网络科技(中国)有限公司 | Advertisement putting cost adjusting method and device, storage medium and electronic equipment |
CN111178954A (en) * | 2019-12-20 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Advertisement putting method and system and electronic equipment |
CN111210255A (en) * | 2019-12-16 | 2020-05-29 | 北京淇瑀信息科技有限公司 | Advertisement pushing method and device and electronic equipment |
CN111222902A (en) * | 2018-11-27 | 2020-06-02 | 阿里巴巴集团控股有限公司 | Advertisement putting method, device, system, computing equipment and storage medium |
CN111476586A (en) * | 2019-01-23 | 2020-07-31 | 阿里巴巴集团控股有限公司 | Advertisement putting method and device, terminal equipment and computer storage medium |
CN111612515A (en) * | 2020-04-11 | 2020-09-01 | 上海淇玥信息技术有限公司 | Advertisement customized delivery platform and method based on time query and electronic equipment |
CN111652647A (en) * | 2020-06-03 | 2020-09-11 | 广州市丰申网络科技有限公司 | Method, system, device and storage medium for automatically uploading advertisement |
CN111667311A (en) * | 2020-06-08 | 2020-09-15 | 腾讯科技(深圳)有限公司 | Advertisement delivery method, related device, equipment and storage medium |
CN111681056A (en) * | 2020-06-11 | 2020-09-18 | 北京焦点新干线信息技术有限公司 | Multi-platform advertisement putting method, device and system |
CN112258213A (en) * | 2020-09-18 | 2021-01-22 | 北京达佳互联信息技术有限公司 | Method, device, equipment and storage medium for determining advertisement putting position |
CN112418901A (en) * | 2020-04-17 | 2021-02-26 | 上海幻电信息科技有限公司 | Advertisement inventory control method and device and storage medium |
CN113256346A (en) * | 2021-06-21 | 2021-08-13 | 广州市丰申网络科技有限公司 | Advertisement delivery account information learning method and device and computer equipment |
CN113298558A (en) * | 2021-05-12 | 2021-08-24 | 阿里巴巴新加坡控股有限公司 | Advertisement putting method, system, equipment and storage medium |
CN113393269A (en) * | 2021-06-11 | 2021-09-14 | 上海明略人工智能(集团)有限公司 | Method and device for determining conversion rate of contact medium, electronic equipment and storage medium |
CN113674013A (en) * | 2021-07-08 | 2021-11-19 | 上海百秋电子商务有限公司 | Advertisement bidding adjustment method and system based on merchant self-defined rules |
CN113781078A (en) * | 2020-09-04 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Data processing method and device, electronic equipment and computer readable medium |
CN114677169A (en) * | 2022-03-16 | 2022-06-28 | 北京奇艺世纪科技有限公司 | Advertisement creative generation method and device |
CN115018533A (en) * | 2022-05-27 | 2022-09-06 | 北京有竹居网络技术有限公司 | Media data processing method, device and equipment |
WO2024082772A1 (en) * | 2022-10-21 | 2024-04-25 | 深圳新度博望科技有限公司 | Method and apparatus for determining advertisement placement strategy, computer device, and storage medium |
-
2018
- 2018-05-14 CN CN201810454811.7A patent/CN108681920A/en active Pending
Cited By (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109598542B (en) * | 2018-11-20 | 2023-10-27 | 创新先进技术有限公司 | Marketing equity throwing method and device and electronic equipment |
CN109598542A (en) * | 2018-11-20 | 2019-04-09 | 阿里巴巴集团控股有限公司 | A kind of put-on method, device and the electronic equipment of equity of marketing |
CN111222902A (en) * | 2018-11-27 | 2020-06-02 | 阿里巴巴集团控股有限公司 | Advertisement putting method, device, system, computing equipment and storage medium |
CN111222902B (en) * | 2018-11-27 | 2024-02-09 | 阿里巴巴集团控股有限公司 | Advertisement putting method, device, system, computing equipment and storage medium |
CN109711866B (en) * | 2018-12-07 | 2021-04-27 | 中国银行股份有限公司 | Bank advertisement putting method, device and system |
CN109711866A (en) * | 2018-12-07 | 2019-05-03 | 中国银行股份有限公司 | A kind of bank advertising put-on method, apparatus and system |
CN111476586A (en) * | 2019-01-23 | 2020-07-31 | 阿里巴巴集团控股有限公司 | Advertisement putting method and device, terminal equipment and computer storage medium |
CN111476586B (en) * | 2019-01-23 | 2023-12-22 | 阿里巴巴集团控股有限公司 | Advertisement putting method and device, terminal equipment and computer storage medium |
CN110135905A (en) * | 2019-05-13 | 2019-08-16 | 重庆天蓬网络有限公司 | Advertisement placement method, system, medium and electronic equipment |
CN111105268A (en) * | 2019-11-28 | 2020-05-05 | 微梦创科网络科技(中国)有限公司 | Advertisement putting cost adjusting method and device, storage medium and electronic equipment |
CN111062746B (en) * | 2019-12-06 | 2023-06-23 | 微梦创科网络科技(中国)有限公司 | Advertisement flow prediction method and device and electronic equipment |
CN111062746A (en) * | 2019-12-06 | 2020-04-24 | 微梦创科网络科技(中国)有限公司 | Advertisement flow estimation method and device and electronic equipment |
CN111210255A (en) * | 2019-12-16 | 2020-05-29 | 北京淇瑀信息科技有限公司 | Advertisement pushing method and device and electronic equipment |
CN111210255B (en) * | 2019-12-16 | 2024-05-17 | 北京淇瑀信息科技有限公司 | Advertisement pushing method and device and electronic equipment |
CN110969490A (en) * | 2019-12-17 | 2020-04-07 | 天津亿玛科技有限公司 | Advertisement putting method and device |
CN111178954A (en) * | 2019-12-20 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Advertisement putting method and system and electronic equipment |
CN111612515A (en) * | 2020-04-11 | 2020-09-01 | 上海淇玥信息技术有限公司 | Advertisement customized delivery platform and method based on time query and electronic equipment |
CN111612515B (en) * | 2020-04-11 | 2024-01-30 | 上海淇玥信息技术有限公司 | Advertisement customization delivery platform and method based on time query and electronic equipment |
CN112418901A (en) * | 2020-04-17 | 2021-02-26 | 上海幻电信息科技有限公司 | Advertisement inventory control method and device and storage medium |
CN112418901B (en) * | 2020-04-17 | 2024-06-07 | 上海幻电信息科技有限公司 | Advertisement inventory control method, device and storage medium |
CN111652647A (en) * | 2020-06-03 | 2020-09-11 | 广州市丰申网络科技有限公司 | Method, system, device and storage medium for automatically uploading advertisement |
CN111667311B (en) * | 2020-06-08 | 2023-12-12 | 腾讯科技(深圳)有限公司 | Advertisement putting method, related device, equipment and storage medium |
CN111667311A (en) * | 2020-06-08 | 2020-09-15 | 腾讯科技(深圳)有限公司 | Advertisement delivery method, related device, equipment and storage medium |
CN111681056B (en) * | 2020-06-11 | 2023-10-10 | 北京焦点新干线信息技术有限公司 | Multi-platform advertisement putting method, device and system |
CN111681056A (en) * | 2020-06-11 | 2020-09-18 | 北京焦点新干线信息技术有限公司 | Multi-platform advertisement putting method, device and system |
CN113781078A (en) * | 2020-09-04 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Data processing method and device, electronic equipment and computer readable medium |
CN112258213A (en) * | 2020-09-18 | 2021-01-22 | 北京达佳互联信息技术有限公司 | Method, device, equipment and storage medium for determining advertisement putting position |
CN113298558A (en) * | 2021-05-12 | 2021-08-24 | 阿里巴巴新加坡控股有限公司 | Advertisement putting method, system, equipment and storage medium |
CN113393269A (en) * | 2021-06-11 | 2021-09-14 | 上海明略人工智能(集团)有限公司 | Method and device for determining conversion rate of contact medium, electronic equipment and storage medium |
CN113393269B (en) * | 2021-06-11 | 2024-03-15 | 上海明略人工智能(集团)有限公司 | Method and device for determining conversion rate of contact media, electronic equipment and storage medium |
CN113256346A (en) * | 2021-06-21 | 2021-08-13 | 广州市丰申网络科技有限公司 | Advertisement delivery account information learning method and device and computer equipment |
CN113674013B (en) * | 2021-07-08 | 2024-04-30 | 上海百秋新网商数字科技有限公司 | Advertisement bidding adjustment method and system based on merchant custom rules |
CN113674013A (en) * | 2021-07-08 | 2021-11-19 | 上海百秋电子商务有限公司 | Advertisement bidding adjustment method and system based on merchant self-defined rules |
CN114677169A (en) * | 2022-03-16 | 2022-06-28 | 北京奇艺世纪科技有限公司 | Advertisement creative generation method and device |
CN115018533A (en) * | 2022-05-27 | 2022-09-06 | 北京有竹居网络技术有限公司 | Media data processing method, device and equipment |
WO2024082772A1 (en) * | 2022-10-21 | 2024-04-25 | 深圳新度博望科技有限公司 | Method and apparatus for determining advertisement placement strategy, computer device, and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108681920A (en) | The method and system launched based on advertising creative optimization advertisement | |
CN108269123B (en) | Advertisement putting control method and device | |
Duffy | Rethinking the prospect theory of patents | |
US11167214B1 (en) | Dynamic game management platform that utilizes predictive analytics to modify game parameters in real-time | |
Bonzon et al. | Catch share design manual: a guide for managers and fishermen | |
CN1564702A (en) | Real-time broadcast of interactive simulations | |
US20120203623A1 (en) | System and method for online advertisement optimization | |
De Vries et al. | The question of generation adequacy in liberalised electricity markets | |
CN110969490A (en) | Advertisement putting method and device | |
CN109615442A (en) | RTB real time bid method based on excitation video ads | |
US11941668B2 (en) | Ad exchange bid optimization with reinforcement learning | |
AU2021200159A1 (en) | Aggregate gaming funds | |
CN109272407A (en) | A kind of major class Asset Allocation class intelligence throwing Gu concentration degree control method | |
Rickard et al. | University licensing of patents for varietal innovations in agriculture | |
KR20010073524A (en) | Device of electronic animal raising using internet and method thereof | |
Schain et al. | Ad exchange–proposal for a new trading agent competition game | |
Osano et al. | Case Study: Biodiversity-and wildlife-tourism-based Payment for Ecosystem Services (PES) in Kenya | |
Willis et al. | Resolving social dilemmas through reward transfer commitments | |
Brown et al. | Attitudes towards data collection, management and development, and the impact of management on economic value of sea angling in the UK | |
KR101632142B1 (en) | System and method for providing contents using benefit logic for high quality contents | |
Stryszowska | Late and multiple bidding in competing second price Internet auctions | |
Grimes | Entrepreneurial Choice: Restoring a Relevant Antitrust Policy | |
WO2012095844A1 (en) | Method and system for electronic tenders | |
Koskela | Pricing economics of video games: a panel data study on the effects of versioning on revenue | |
Naghavi | Multilateral environmental agreements and trade obligations: a theoretical analysis of the Doha proposal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181019 |
|
RJ01 | Rejection of invention patent application after publication |